Welcome to the InfoSci Platform
Reference Hub1
FaceTimeMap: Multi-Level Bitmap Index for Temporal Querying of Faces in Videos

FaceTimeMap: Multi-Level Bitmap Index for Temporal Querying of Faces in Videos

Buddha Shrestha, Haeyong Chung, Ramazan S. Aygün
Copyright: © 2019 |Volume: 10 |Issue: 2 |Pages: 23
ISSN: 1947-8534|EISSN: 1947-8542|EISBN13: 9781522565338|DOI: 10.4018/IJMDEM.2019040103
Cite Article Cite Article

MLA

Shrestha, Buddha, et al. "FaceTimeMap: Multi-Level Bitmap Index for Temporal Querying of Faces in Videos." IJMDEM vol.10, no.2 2019: pp.37-59. http://doi.org/10.4018/IJMDEM.2019040103

APA

Shrestha, B., Chung, H., & Aygün, R. S. (2019). FaceTimeMap: Multi-Level Bitmap Index for Temporal Querying of Faces in Videos. International Journal of Multimedia Data Engineering and Management (IJMDEM), 10(2), 37-59. http://doi.org/10.4018/IJMDEM.2019040103

Chicago

Shrestha, Buddha, Haeyong Chung, and Ramazan S. Aygün. "FaceTimeMap: Multi-Level Bitmap Index for Temporal Querying of Faces in Videos," International Journal of Multimedia Data Engineering and Management (IJMDEM) 10, no.2: 37-59. http://doi.org/10.4018/IJMDEM.2019040103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this article, the authors study bitmap indexing for temporal querying of faces that appear in videos. Since the bitmap index is originally designed to select a set of records that satisfy a value in the domain of the attribute, there is no clear strategy for how to apply it for temporal querying. Accordingly, the authors introduce a multi-level bitmap index that the authors call “FaceTimeMap” for temporal querying of faces in videos. The first level of the FaceTimeMap index is used for determining whether a person appears in a video or not, whereas the second level of the index is used for determining intervals when a person appears. First, the authors analyze the co-appearance query where two or more people appear simultaneously in a video, and then examine next-appearance query where a person appears right after another person. In addition, to consider the gap between the appearance of people, the authors study eventual- and prior-appearance queries. Queries are satisfied by applying bitwise operations on the FaceTimeMap index. The authors provide some performance studies associated with this index.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.